A Generalized Additive Model (GAM) is a Generalized Linear Model in which the linearity in the linear predictor is relaxed; it is specified in terms of a sum of smooth functions of predictor variables. Various techniques canbe employed for actually fitting a generalized additive model, such as the backfitting. Another approach that for fittin a GAM is by using regression splines and a penalized likelihood to obtain estimates. In this project, GAM based on regression splines will be considered as well as applications to real data analysis.
News published in Agência FAPESP Newsletter about the scholarship: